Repository navigation
Epic: absorb Lauren Tan's and Matt Pocock's agent workflows (poteto-review) #7555
Description
Brief
Goal. Absorb Lauren Tan's (poteto, pstack) and Matt Pocock's agent workflows into this
marketplace, item by item as the owner decided them, because the owner runs 5-20 sessions and wants
their problem-solving moves (codify on recurrence, non-author verification, narrow ready PRs,
catch-up, grilling, paved paths) working in his own skills and plans (GUIDE D0-D119; register
Q1-Q589).
Scope. The 23 buildable threads of the design record, delivered in its 11-step dependency
order; the 15 deferred threads filed as parked sub-issues (14 issues: Delivery shape is settled by
Q589 and gets none; Cursor compatibility is the active Q579 research item); the probes the design
record requires before adoption; the carried defect fixes Q148 allows. Out of scope: everything the
design record lists as out of scope or declined.
Delivery shape (Q589, GUIDE D119, owner-approved). One epic as spec container; one sub-issue per
buildable thread in dependency order with native blocked-by edges; slice issues under a thread only
where it needs more than one PR; narrow PRs open ready unless a multi-session container (Q501,
Q585); deferred threads as parked sub-issues. Basis: Matt's to-tickets (slices sized to one context
window, blockers first, sub-issues) and Lauren's "prefer five narrow PRs to one large PR".
Hard constraints that bind implementation
- C3: fewer, larger skills with actions and progressive disclosure; cross-skill use only as
/plugin:skill, never by path. - C4: tool-neutral via adapters (ADR 0060); configurable defaults in the conventions home.
- C5 as amended by Q567: unattended merge only on a passing verdict from a verifier other than the
author, once Q519's verifier exists; no report-only phase (D96); Dependabot is required checks
only. - C13 (amended, Q575): no agent acts until the owner's intent is codified; recommendations are
researched against official sources; routine actions follow the research-depth setting, default
"cite what is in context". - C14: skills never couple to this repo's own conventions; plugin defaults are fallbacks; project,
team and user instructions win. - C15: prefer native mechanisms; inject nothing into a working session the user did not ask for.
- C17: a preference where reasonable consumers differ ships as a setting with a named default,
basis and scope; fixed floors only tighten (D79, Q574, D96, D88, D100, Q131, the C13 intent gate). - Evidence before autonomy (GUIDE D1): nothing widens unattended authority (merge, close, write)
before the probe or eval that gates it passes; a check is recorded only after it fails on a
planted or past violation and passes after revert (D22, Q115). - Label the origin: every sub-issue and PR body names the origin of the decision it carries as
Lauren's, Matt's, owner's, ours or combined. - Repository rules: AGENTS.md "Code Review Rules" (a skill-body cut ships only with eval evidence
of no loss; volatile upstream specifics are pointers with as-of date and recheck trigger;## Next
sections) and the AGENTS.md stop list (another repo, user-scope config, grant changes).
Acceptance criteria
- The epic's 23 thread sub-issues are closed by merged PRs, or carry a recorded probe result that
stops adoption with the owner's sign-off; the 13 parked sub-issues stay open with their reopen
trigger, and the 1 active Cursor research item (Q579) reports. - Every probe the design record requires before adoption has a recorded result on its slice issue
before the work it gates merges. - Every new check ships with its proof script output: fails on the old code, passes on current
(D22). - Every cut to an existing skill body cites before/after eval results in its PR (AGENTS.md).
- Every setting in the design record's settings table resolves through the config cascade from the
Settings resolution thread with its named default. - No PR merges unattended before the Merge authority thread's verifier and planted-defect run pass.
Assumptions (the design record's captured assumptions 1-14 carry over unchanged; the riskiest
four are probes or questions in this plan):
- A1 (assumption 1): a same-vendor non-author verifier catches enough defects to be the
only merge gate; settled by the Merge authority thread's planted-defect run. - A2 (assumption 2, Q586): consumers run GitHub first-class; every GitHub feature degrades through
an adapter. - A3 (assumption 3, Q587): plan usage tolerates the added model steps; each step is a setting with
the per-item usage rollup (Q58) as the measure. - A4 (assumption 4): the lanes App token broker can mint
statuses: write,discussions: write,
issue-field writes and workflow-triggering pushes; settled by reading the broker (see the
broker-mint slice): it grantscontents,pull_requestsandissuesonly. - A5: the existing
pr-feedback-dispatch.ymllane is the findings lane Q512 describes, so the PR
pipeline thread reconciles rather than rebuilds it.
Execution shape: per-item PRs
Activity
32 remaining items
kyle-sexton commentedon Oct 20, 2026
Decision recorded. Evening realignment round, owner answers in the poteto-review session (2026-10-20, question dialog):
pr_open_statelike attended ones (feat(source-control): ship the pr_open_state default as ready #8655 amended).pre_readyturns off recordsskippedand the ready flip proceeds.kyle-sexton commentedon Oct 24, 2026
Released for re-triage under the owner's 2026-10-24 rule: an issue stops for a person only for an intent or vision question, a security call, a host or attended run, or spend outside prepaid credit. The hold label came off and intake triage runs again now; it re-applies a hold, with a numbered question, when one of those applies.
To hold this issue again, add
needs-human(orstatus: needs-decision) and say why in a comment.melodic-automation-lanes commentedon Oct 24, 2026
Not admitted to the issue lane yet: Size large: the split into sub-issues at intake is pending (owner Q93).
melodic-automation-lanes commentedon Oct 24, 2026
Refinement. A read-only run explored this repository, searched its issues and pull requests, and read the allowed docs to draft what follows. It is model text, to check, not instructions.
Intended outcome: This epic is a spec container whose 23 thread sub-issues and 14 parked sub-issues deliver the work, so no lane run should work it directly.
Related work
Open questions
RECOMMENDED: Yes. Keep it as a work-map container that the lane never picks up, and refine each thread sub-issue on its own. Basis: judgment: the body is a container with 23 threads and 14 parked issues, the delivery shape is settled by Q589, and the intake comment says it proceeds through sub-issues and not one PR.
RECOMMENDED: Add a task list to the body that links each thread and slice issue by number, in dependency order. The criteria can then be checkable, for example every linked thread issue is closed. Basis: judgment: the thin reason is that the body has no task list, and the criteria depend on counts (23, 13 or 14 parked) that the body cannot verify.
RECOMMENDED: Confirm the count against the filed parked issues. The 14 in the scope may include the Cursor research item, which would leave 13 parked plus 1 active. Basis: judgment: the two numbers in the body differ, and the scope's own wording about Q579 suggests that is the reason.
RECOMMENDED: Amend criterion 6 to match the 2026-10-20 decision comment, so it no longer requires the planted-defect run before an unattended merge, and say whether the Merge authority verifier alone gates it. Basis: judgment: criterion 6 and constraint C5 conflict with the owner's decision that #7719 does not gate the flip.
RECOMMENDED: Yes. The 2026-10-24 comment releases it under the owner's new rule, and no remaining open item meets that rule, so the status: needs-decision label can come off once the body is amended. Basis: judgment: the 2026-10-24 release comment and the two Decision recorded comments settle the earlier open decisions.
Sources read
Automated refinement by the lanes App. Answer with a comment whose first line is
**Decision recorded.**.kyle-sexton commentedon Oct 25, 2026
Decision recorded. The open questions in intake's refinement (#7555 (comment)) are answered by owner decisions already on this issue. Nothing new is decided here.
Sources, quoted verbatim:
Q2 (which sub-issues exist) and Q3 (13 or 14 parked) are facts, not decisions: the native sub-issue list on this issue answers them.
Acceptance criteria, converted from the body's criteria list, wording unchanged except criterion 6. The epic closes through its sub-issues, never by a lane run on it.